Borrowing it
Nothing to install: this file belongs to whtoo/How_to_implment_PL_in_Antlr4. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/whtoo/How_to_implment_PL_in_Antlr4/main/.claude/skills/ep-navigator/SKILL.mdgit clone --depth 1 https://github.com/whtoo/How_to_implment_PL_in_Antlr4Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/whtoo/how_to_implment_pl_in_antlr4/ep-navigator)<a href="https://agentmods.dev/skills/whtoo/how_to_implment_pl_in_antlr4/ep-navigator"><img src="https://agentmods.dev/badge/skills/whtoo/how_to_implment_pl_in_antlr4/ep-navigator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/whtoo/how_to_implment_pl_in_antlr4/ep-navigator"><img src="https://agentmods.dev/badge/skills/whtoo/how_to_implment_pl_in_antlr4/ep-navigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01338 |
| Opus 5 | $0.00014 | $0.00669 |
| Sonnet 5 | $0.00005 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
ep-navigator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EP导航专家
🎯 垂直职责
单一职责: EP项目知识图谱导航和路由决策
📊 EP依赖关系图
graph TD
%% 基础层
EP1[EP1: Lexer] --> EP2[EP2: Parser]
EP2 --> EP3[EP3: AST]
EP3 --> EP4[EP4: Listener]
EP4 --> EP5[EP5: Visitor]
EP5 --> EP6[EP6: Symbol Table]
EP6 --> EP7[EP7: Types]
EP7 --> EP8[EP8: Type Checking]
EP8 --> EP9[EP9: Scopes]
EP9 --> EP10[EP10: Interpreter]
%% 编译器层
EP10 --> EP11[EP11: IR Design]
EP11 --> EP12[EP12: IR Gen]
EP12 --> EP13[EP13: Bytecode]
EP13 --> EP14[EP14: VM Entry]
EP14 --> EP15[EP15: Function Call]
EP15 --> EP16[EP16: Control Flow]
EP16 --> EP17[EP17: Arrays]
%% 后端分支
EP17 --> EP18[EP18: Stack VM]
EP17 --> EP18R[EP18R: Register VM]
EP17 --> EP19[EP19: Compiler Interpreter]
EP17 --> EP20[EP20: Full Compiler]
%% 优化层
EP20 --> EP21[EP21: Optimization]
%% 虚拟机分支
EP18 -.-> EP18R
EP19 -.-> EP20
🚀 快速路由表
| 用户意图 | 目标EP | 加载记忆 | 加载技能 |
|---|---|---|---|
| "词法/语法问题" | EP1-EP5 | 无需 | antlr4-dev |
| "符号表/类型检查" | EP6-EP10 | EP{编号}.md | compiler-dev |
| "IR/代码生成" | EP11-EP17 | EP{编号}.md | compiler-dev |
| "虚拟机" | EP18, EP18R | EP18.md | vm-dev |
| "编译器完整流程" | EP19, EP20 | EP19.md, EP20.md | compiler-dev |
| "优化/SSA" | EP21 | EP21_TECH_MEM.md | compiler-dev |
| "文档编写" | - | - | doc-dev |
| "测试开发" | - | - | test-dev |
📦 核心能力
1. EP识别
从用户输入自动识别目标EP：
输入: "在ep18中添加垃圾回收"
→ 识别: EP18
→ 加载: docs/ep-memory/EP18.md
→ 加载技能: vm-dev
2. 跨EP对比
输入: "对比ep18和ep18r的ABI设计"
→ 加载: EP18.md + EP18R.md
→ 对比维度: 调用约定、栈帧布局、参数传递
→ 输出: 标准化对比表
3. 依赖分析
输入: "修改EP5的Visitor接口"
→ 分析: 影响EP6-EP21所有使用Visitor的模块
→ 报告: 受影响EP列表 + 风险评估
🔗 关系图
→ 被所有技能依赖 (优先加载) ← 无依赖
📂 关键文件映射
| EP | 核心目录 | 入口文件 | 关键记忆 |
|---|---|---|---|
| EP1-5 | ep20/src/main/antlr4/ |
Cymbol.g4 |
无 |
| EP6-10 | ep20/src/main/java/org/teachfx/antlr4/ep20/symtab/ |
Symbol.java |
EP{编号}.md |
| EP11-17 | ep20/src/main/java/org/teachfx/antlr4/ep20/ |
Compiler.java |
EP{编号}.md |
| EP18 | ep18/src/main/java/org/teachfx/antlr4/ep18/stackvm/ |
CymbolStackVM.java |
EP18.md |
| EP18R | ep18r/src/main/java/org/teachfx/antlr4/ep18r/regvm/ |
CymbolRegisterVM.java |
EP18R.md |
| EP19 | ep19/src/main/java/org/teachfx/antlr4/ep19/ |
Compiler.java |
EP19.md |
| EP20 | ep20/src/main/java/org/teachfx/antlr4/ep20/ |
Compiler.java |
EP20.md |
| EP21 | ep21/src/main/java/org/teachfx/antlr4/ep21/ |
Optimizer.java |
EP21_TECH_MEM.md |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 130 lines · 27 tokens per session scan A 77b9786d1df3
ep-navigator is a skill published in the GitHub repository whtoo/How_to_implment_PL_in_Antlr4 (34 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 27 tokens to every session and 1,338 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
biomed-skill-router
Find the most suitable skill for a given biomedical task. Use this skill when: (1) You are unsure which skill to use for a specific biomedical task, (2) You want to discover available skills for a particular domain, (3) You need to compare multiple skills for a given use case.
jupyter-notebook
Use when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and helper script for reproducible notebook structure and safer editing.
absolute-docs
Diátaxis-driven documentation for AI coding agents: write, improve, or audit tutorials, how-tos, reference, explanation, and developer docs (README, CONTRIBUTING, ADRs). Detects the docs stack; gates on the outline before writing prose; verifies every claim against the code before it ships. Triggers on "absolute…
reiseroute
Route planning from A to B via OSRM (Open Source Routing Machine). Supports car, bicycle and pedestrian. No API key required.
staircase-routing
Eigenständige Navigations- und Routing-Strategie, die Verzeichnishierarchien nach oben und unten nach Wegweiser-Dokumenten wie CLAUDE.md, AGENTS.md, README.md und RULES.md sowie nach nutzerkonfigurierbaren Stichwörtern durchsucht. Die Konfiguration erfolgt über staircase-config.json oder config.json. Auch als…
ttb-skill-swiftui
SwiftUI full-stack development for TTBaseUIKit apps. Use for SwiftUI/SUIBaseView/TTBaseSUI screens, reusable SwiftUI views, list/grid screens, SwiftUI ViewModels, and native SwiftUI fallback when TTBaseSUI has no equivalent. Supports English and Vietnamese user prompts. iOS 14+.